Views
No views yet
pip install transformers1from transformers import AutoTokenizer, AutoModelForSequenceClassification, TextClassificationPipeline
2model_name = 'qanastek/51-languages-classifier'
3tokenizer = AutoTokenizer.from_pretrained(model_name)
4model = AutoModelForSequenceClassification.from_pretrained(model_name)
5classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer)
6res = classifier("פרק הבא בפודקאסט בבקשה")
7print(res)[{'label': 'he-IL', 'score': 0.9998375177383423}]Afrikaans - South Africa (af-ZA)Amharic - Ethiopia (am-ET)Arabic - Saudi Arabia (ar-SA)Azeri - Azerbaijan (az-AZ)Bengali - Bangladesh (bn-BD)Chinese - China (zh-CN)Chinese - Taiwan (zh-TW)Danish - Denmark (da-DK)German - Germany (de-DE)Greek - Greece (el-GR)English - United States (en-US)Spanish - Spain (es-ES)Farsi - Iran (fa-IR)Finnish - Finland (fi-FI)French - France (fr-FR)Hebrew - Israel (he-IL)Hungarian - Hungary (hu-HU)Armenian - Armenia (hy-AM)Indonesian - Indonesia (id-ID)Icelandic - Iceland (is-IS)Italian - Italy (it-IT)Japanese - Japan (ja-JP)Javanese - Indonesia (jv-ID)Georgian - Georgia (ka-GE)Khmer - Cambodia (km-KH)Korean - Korea (ko-KR)Latvian - Latvia (lv-LV)Mongolian - Mongolia (mn-MN)Malay - Malaysia (ms-MY)Burmese - Myanmar (my-MM)Norwegian - Norway (nb-NO)Dutch - Netherlands (nl-NL)Polish - Poland (pl-PL)Portuguese - Portugal (pt-PT)Romanian - Romania (ro-RO)Russian - Russia (ru-RU)Slovanian - Slovania (sl-SL)Albanian - Albania (sq-AL)Swedish - Sweden (sv-SE)Swahili - Kenya (sw-KE)Hindi - India (hi-IN)Kannada - India (kn-IN)Malayalam - India (ml-IN)Tamil - India (ta-IN)Telugu - India (te-IN)Thai - Thailand (th-TH)Tagalog - Philippines (tl-PH)Turkish - Turkey (tr-TR)Urdu - Pakistan (ur-PK)Vietnamese - Vietnam (vi-VN)Welsh - United Kingdom (cy-GB)1 precision recall f1-score support
2
3 af-ZA 0.9821 0.9805 0.9813 2974
4 am-ET 1.0000 1.0000 1.0000 2974
5 ar-SA 0.9809 0.9822 0.9815 2974
6 az-AZ 0.9946 0.9845 0.9895 2974
7 bn-BD 0.9997 0.9990 0.9993 2974
8 cy-GB 0.9970 0.9929 0.9949 2974
9 da-DK 0.9575 0.9617 0.9596 2974
10 de-DE 0.9906 0.9909 0.9908 2974
11 el-GR 0.9997 0.9973 0.9985 2974
12 en-US 0.9712 0.9866 0.9788 2974
13 es-ES 0.9825 0.9842 0.9834 2974
14 fa-IR 0.9940 0.9973 0.9956 2974
15 fi-FI 0.9943 0.9946 0.9945 2974
16 fr-FR 0.9963 0.9923 0.9943 2974
17 he-IL 1.0000 0.9997 0.9998 2974
18 hi-IN 1.0000 0.9980 0.9990 2974
19 hu-HU 0.9983 0.9950 0.9966 2974
20 hy-AM 1.0000 0.9993 0.9997 2974
21 id-ID 0.9319 0.9291 0.9305 2974
22 is-IS 0.9966 0.9943 0.9955 2974
23 it-IT 0.9698 0.9926 0.9811 2974
24 ja-JP 0.9987 0.9963 0.9975 2974
25 jv-ID 0.9628 0.9744 0.9686 2974
26 ka-GE 0.9993 0.9997 0.9995 2974
27 km-KH 0.9867 0.9963 0.9915 2974
28 kn-IN 1.0000 0.9993 0.9997 2974
29 ko-KR 0.9917 0.9997 0.9956 2974
30 lv-LV 0.9990 0.9950 0.9970 2974
31 ml-IN 0.9997 0.9997 0.9997 2974
32 mn-MN 0.9987 0.9966 0.9976 2974
33 ms-MY 0.9359 0.9418 0.9388 2974
34 my-MM 1.0000 0.9993 0.9997 2974
35 nb-NO 0.9600 0.9533 0.9566 2974
36 nl-NL 0.9850 0.9748 0.9799 2974
37 pl-PL 0.9946 0.9923 0.9934 2974
38 pt-PT 0.9885 0.9798 0.9841 2974
39 ro-RO 0.9919 0.9916 0.9918 2974
40 ru-RU 0.9976 0.9983 0.9980 2974
41 sl-SL 0.9956 0.9939 0.9948 2974
42 sq-AL 0.9936 0.9896 0.9916 2974
43 sv-SE 0.9902 0.9842 0.9872 2974
44 sw-KE 0.9867 0.9953 0.9910 2974
45 ta-IN 1.0000 1.0000 1.0000 2974
46 te-IN 1.0000 0.9997 0.9998 2974
47 th-TH 1.0000 0.9983 0.9992 2974
48 tl-PH 0.9929 0.9899 0.9914 2974
49 tr-TR 0.9869 0.9872 0.9871 2974
50 ur-PK 0.9983 0.9929 0.9956 2974
51 vi-VN 0.9993 0.9973 0.9983 2974
52 zh-CN 0.9812 0.9832 0.9822 2974
53 zh-TW 0.9832 0.9815 0.9823 2974
54
55 accuracy 0.9889 151674
56 macro avg 0.9889 0.9889 0.9889 151674
57weighted avg 0.9889 0.9889 0.9889 151674